A methodological approach to classify typical and atypical pigment network patterns for melanoma diagnosis

Sameena Pathan, K. Gopalakrishna Prabhu, P. C. Siddalingaswamy

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

The pigment network is considered as one of the most histopathologically relevant indicator of melanoma. The objective of this empirical study is to design a novel automatic system for detection of pigment network and provide a differentiation between typical and atypical network patterns. The algorithm design consists a set of sequential stages. Pigment network masks are detected using a bank of 2D Gabor filters, and a set of pigment network features are extracted to determine the role of pigment network in the diagnosis of the lesion. In the second stage, a machine learning process is carried out using the rules generated from the pigment network masks to identify the typical and atypical pigment network patterns. The proposed methodology was tested on the PH2 dataset of 200 images, obtaining an average sensitivity of 96%, specificity of 100% and accuracy of 96.7% for lesion diagnosis, and an average sensitivity, specificity and accuracy of 84.6%, 88.7% and 86.7% respectively, for pigment network classification. The proposed system stands out amongst the few state of art literatures reported in the context of dermoscopic image analysis in terms of performance and methodologies adopted, thus proving the reliability of the proposed study.

Original languageEnglish
Pages (from-to)25-37
Number of pages13
JournalBiomedical Signal Processing and Control
Volume44
DOIs
Publication statusPublished - 01-07-2018

Fingerprint

Masks
Pigments
Melanoma
Sensitivity and Specificity
Gabor filters
Image analysis
Learning systems
Datasets
Machine Learning

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Health Informatics

Cite this

@article{e443ec64d8d644b69465ce4137bff256,
title = "A methodological approach to classify typical and atypical pigment network patterns for melanoma diagnosis",
abstract = "The pigment network is considered as one of the most histopathologically relevant indicator of melanoma. The objective of this empirical study is to design a novel automatic system for detection of pigment network and provide a differentiation between typical and atypical network patterns. The algorithm design consists a set of sequential stages. Pigment network masks are detected using a bank of 2D Gabor filters, and a set of pigment network features are extracted to determine the role of pigment network in the diagnosis of the lesion. In the second stage, a machine learning process is carried out using the rules generated from the pigment network masks to identify the typical and atypical pigment network patterns. The proposed methodology was tested on the PH2 dataset of 200 images, obtaining an average sensitivity of 96{\%}, specificity of 100{\%} and accuracy of 96.7{\%} for lesion diagnosis, and an average sensitivity, specificity and accuracy of 84.6{\%}, 88.7{\%} and 86.7{\%} respectively, for pigment network classification. The proposed system stands out amongst the few state of art literatures reported in the context of dermoscopic image analysis in terms of performance and methodologies adopted, thus proving the reliability of the proposed study.",
author = "Sameena Pathan and Prabhu, {K. Gopalakrishna} and Siddalingaswamy, {P. C.}",
year = "2018",
month = "7",
day = "1",
doi = "10.1016/j.bspc.2018.03.017",
language = "English",
volume = "44",
pages = "25--37",
journal = "Biomedical Signal Processing and Control",
issn = "1746-8094",
publisher = "Elsevier BV",

}

A methodological approach to classify typical and atypical pigment network patterns for melanoma diagnosis. / Pathan, Sameena; Prabhu, K. Gopalakrishna; Siddalingaswamy, P. C.

In: Biomedical Signal Processing and Control, Vol. 44, 01.07.2018, p. 25-37.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A methodological approach to classify typical and atypical pigment network patterns for melanoma diagnosis

AU - Pathan, Sameena

AU - Prabhu, K. Gopalakrishna

AU - Siddalingaswamy, P. C.

PY - 2018/7/1

Y1 - 2018/7/1

N2 - The pigment network is considered as one of the most histopathologically relevant indicator of melanoma. The objective of this empirical study is to design a novel automatic system for detection of pigment network and provide a differentiation between typical and atypical network patterns. The algorithm design consists a set of sequential stages. Pigment network masks are detected using a bank of 2D Gabor filters, and a set of pigment network features are extracted to determine the role of pigment network in the diagnosis of the lesion. In the second stage, a machine learning process is carried out using the rules generated from the pigment network masks to identify the typical and atypical pigment network patterns. The proposed methodology was tested on the PH2 dataset of 200 images, obtaining an average sensitivity of 96%, specificity of 100% and accuracy of 96.7% for lesion diagnosis, and an average sensitivity, specificity and accuracy of 84.6%, 88.7% and 86.7% respectively, for pigment network classification. The proposed system stands out amongst the few state of art literatures reported in the context of dermoscopic image analysis in terms of performance and methodologies adopted, thus proving the reliability of the proposed study.

AB - The pigment network is considered as one of the most histopathologically relevant indicator of melanoma. The objective of this empirical study is to design a novel automatic system for detection of pigment network and provide a differentiation between typical and atypical network patterns. The algorithm design consists a set of sequential stages. Pigment network masks are detected using a bank of 2D Gabor filters, and a set of pigment network features are extracted to determine the role of pigment network in the diagnosis of the lesion. In the second stage, a machine learning process is carried out using the rules generated from the pigment network masks to identify the typical and atypical pigment network patterns. The proposed methodology was tested on the PH2 dataset of 200 images, obtaining an average sensitivity of 96%, specificity of 100% and accuracy of 96.7% for lesion diagnosis, and an average sensitivity, specificity and accuracy of 84.6%, 88.7% and 86.7% respectively, for pigment network classification. The proposed system stands out amongst the few state of art literatures reported in the context of dermoscopic image analysis in terms of performance and methodologies adopted, thus proving the reliability of the proposed study.

UR - http://www.scopus.com/inward/record.url?scp=85045284671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045284671&partnerID=8YFLogxK

U2 - 10.1016/j.bspc.2018.03.017

DO - 10.1016/j.bspc.2018.03.017

M3 - Article

AN - SCOPUS:85045284671

VL - 44

SP - 25

EP - 37

JO - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

SN - 1746-8094

ER -